mealie-mcp/mealie_mcp/normalize.py

"""Text normalization for Swedish recipe content.

Pure functions, no I/O. These encode pitfalls verified against Fredrik's live
Mealie instance — see resources/import-pitfalls.md.
"""
from __future__ import annotations

import re
from decimal import ROUND_HALF_UP, Decimal

#: Campaign/navigation suffixes seen appended to imported titles, notably from Köket.
TITLE_JUNK_SUFFIXES = (
    "- se & gör",
    "- se och gör",
    "| Köket.se",
    "| Köket",
    "- Recept",
    "- recept",
)

#: Placeholder text Mealie writes when a scrape fails to find real content.
EXTRACTION_FAILURE_MARKERS = (
    "Could not detect ingredients",
    "Could not detect instructions",
)

#: English units/labels that must not survive into a finished Swedish recipe.
ENGLISH_LEFTOVERS = (
    "cup", "cups", "tbsp", "tsp", "tablespoon", "teaspoon",
    "oz", "ounce", "lb", "pound", "clove", "cloves",
    "servings", "ingredients", "instructions",
)

_DECIMAL_COMMA = re.compile(r"(?<=\d),(?=\d)")
_WHITESPACE = re.compile(r"\s+")


def normalize_for_parser(line: str) -> str:
    """Return a variant of a Swedish ingredient line the Mealie parser handles better.

    Only converts decimal comma to decimal point (``4,7 dl`` -> ``4.7 dl``).
    The result is for the parser only; the original line stays canonical for
    ``display``/``note``, because the parser mangles Swedish text.
    """
    return _WHITESPACE.sub(" ", _DECIMAL_COMMA.sub(".", line)).strip()


def clean_title(title: str) -> str:
    """Strip campaign/navigation junk that import scrapers append to recipe titles."""
    cleaned = title.strip()
    changed = True
    while changed:
        changed = False
        for suffix in TITLE_JUNK_SUFFIXES:
            if cleaned.lower().endswith(suffix.lower()):
                cleaned = cleaned[: -len(suffix)].strip(" -|–")
                changed = True
    return _WHITESPACE.sub(" ", cleaned).strip()


def slugify(title: str) -> str:
    """Build a Mealie-style slug from a Swedish title, preserving å/ä/ö transliteration."""
    text = title.lower()
    for source, target in (("å", "a"), ("ä", "a"), ("ö", "o"), ("é", "e"), ("&", "och")):
        text = text.replace(source, target)
    text = re.sub(r"[^a-z0-9]+", "-", text)
    return text.strip("-")


def find_english_leftovers(text: str) -> list[str]:
    """Return English unit/label words still present in supposedly Swedish content."""
    lowered = text.lower()
    return [word for word in ENGLISH_LEFTOVERS if re.search(rf"\b{re.escape(word)}\b", lowered)]


def has_extraction_failure(recipe: dict) -> bool:
    """Detect Mealie's 'could not detect' placeholders anywhere in a recipe."""
    haystack = [recipe.get("description") or ""]
    haystack += [i.get("display") or i.get("note") or "" for i in recipe.get("recipeIngredient") or []]
    haystack += [s.get("text") or "" for s in recipe.get("recipeInstructions") or []]
    blob = " ".join(haystack)
    return any(marker in blob for marker in EXTRACTION_FAILURE_MARKERS)


def ingredient_display_lines(recipe: dict) -> list[str]:
    """Extract the human-facing ingredient lines, preferring display over note."""
    lines = []
    for item in recipe.get("recipeIngredient") or []:
        text = item.get("display") or item.get("note") or ""
        if not text:
            food = item.get("food") or {}
            text = food.get("name") or ""
        lines.append(text)
    return lines


#: One amount: a decimal ("4,7"), a fraction ("1/2"), or a mixed number ("1 1/2").
_AMOUNT = r"\d+(?:[.,]\d+)?(?:\s+\d+/\d+)?|\d+/\d+"

#: A leading amount in a Swedish ingredient line, optionally a range:
#: "800 g ...", "4,7 dl ...", "1 klyfta ...", "1-1,5 msk ...", "1 1/2 msk ...".
_LEADING_AMOUNT = re.compile(
    rf"^\s*(?P<low>{_AMOUNT})(?:\s*[-–]\s*(?P<high>{_AMOUNT}))?(?=\s|[^\d.,/-]|$)"
)


def parse_amount(raw: str) -> Decimal:
    """Read a Swedish/ASCII amount: ``4,7``, ``1/2``, or the mixed number ``1 1/2``."""
    text = raw.strip().replace(",", ".")
    whole = Decimal(0)
    if " " in text:
        head, text = text.split(None, 1)
        whole = Decimal(head)
    if "/" in text:
        numerator, denominator = text.split("/", 1)
        return whole + Decimal(numerator) / Decimal(denominator)
    return whole + Decimal(text)


def format_amount(value: Decimal) -> str:
    """Render a scaled amount the way the recipe library writes them.

    Whole numbers lose the decimal part (``1200``, not ``1200.0``) and fractions
    use the Swedish decimal comma (``1,5``) to match the stored ingredient lines.
    """
    quantized = value.quantize(Decimal("0.1"), rounding=ROUND_HALF_UP)
    if quantized == quantized.to_integral_value():
        return str(int(quantized))
    return format(quantized, "f").replace(".", ",")


def scale_line(line: str, factor: Decimal) -> tuple[str, bool]:
    """Scale the leading amount of an ingredient line.

    Returns the line and whether anything was scaled. The amount is read from the
    display text rather than the structured ``quantity`` field, because unparsed
    recipes carry ``quantity: 0.0`` while the real number lives in the text — and
    because ``str(800.0)`` never substring-matches ``"800 g ..."``.
    """
    match = _LEADING_AMOUNT.match(line)
    if not match:
        return line, False

    def scaled(raw: str) -> str:
        return format_amount(parse_amount(raw) * factor)

    low = scaled(match.group("low"))
    high = match.group("high")
    # A range must move at both ends: "1-1,5 msk" doubled is "2-3 msk", not "2-1,5 msk".
    replacement = f"{low}-{scaled(high)}" if high else low
    return line[: match.start("low")] + replacement + line[match.end() :], True


def looks_mangled(line: str) -> bool:
    """Heuristic for parser-damaged display text.

    Verified failure modes: vulgar/composed fractions (``47⁄10 liter``), duplicated
    units, and stray fraction glyphs the Mealie parser emits for Swedish rows.
    """
    if any(glyph in line for glyph in ("⁄", "½", "¼", "¾", "⅓", "⅔")):
        return True
    # Duplicated words, but only alphabetic ones: "2 dl dl grädde" is parser damage,
    # while the mixed number in "1 1/2 msk tomatpuré" is perfectly readable.
    if re.search(r"\b([^\W\d_]+)\s+\1\b", line, flags=re.IGNORECASE):
        return True
    return False